[llvm] [offload] Remove bad assert in StaticLoopChunker::Distribute (PR #132705)

[via llvm-commits]

https://github.com/macurtis-amd created https://github.com/llvm/llvm-project/pull/132705

When building with asserts enabled, this can actually cause strange miscompilations because an incorrect llvm.assume is generated at the point of the assertion.

>From 269ee210218631fcae1ad1b56b70c648c3cdfa74 Mon Sep 17 00:00:00 2001
From: Matthew Curtis <macurtis at amd.com>
Date: Fri, 21 Mar 2025 09:04:52 -0500
Subject: [PATCH] [offload] Remove bad assert in StaticLoopChunker::Distribute

When building with asserts enabled, this can actually cause strange
miscompilations because an incorrect llvm.assume is generated at the point of
the assertion.
---
 offload/DeviceRTL/src/Workshare.cpp           |  1 -
 .../fortran/target-teams-dist-nest-par.f90    | 26 +++++++++++++++++++
 2 files changed, 26 insertions(+), 1 deletion(-)
 create mode 100644 offload/test/offloading/fortran/target-teams-dist-nest-par.f90

diff --git a/offload/DeviceRTL/src/Workshare.cpp b/offload/DeviceRTL/src/Workshare.cpp
index de4ed2e2102a6..861b9ca371ccd 100644
--- a/offload/DeviceRTL/src/Workshare.cpp
+++ b/offload/DeviceRTL/src/Workshare.cpp
@@ -820,7 +820,6 @@ template <typename Ty> class StaticLoopChunker {
     Ty ThreadChunk = 0;
     Ty NumThreads = 1;
     Ty TId = 0;
-    ASSERT(TId == mapping::getThreadIdInBlock(), "Bad thread id");
 
     // All teams need to participate.
     Ty NumBlocks = mapping::getNumberOfBlocksInKernel();
diff --git a/offload/test/offloading/fortran/target-teams-dist-nest-par.f90 b/offload/test/offloading/fortran/target-teams-dist-nest-par.f90
new file mode 100644
index 0000000000000..dfde1b98f3c86
--- /dev/null
+++ b/offload/test/offloading/fortran/target-teams-dist-nest-par.f90
@@ -0,0 +1,26 @@
+! REQUIRES: flang, amdgpu
+
+! RUN: %libomptarget-compile-fortran-generic
+! RUN: %libomptarget-run-generic 2>&1 | %fcheck-generic
+program main
+  integer :: array(10) = 0
+  integer :: x, y, z
+  !$omp target
+  !$omp teams distribute private(x, y)
+  OuterLoopOne: do x=1,1
+     array(2) = 42
+     OuterLoopTwo: do y=1,1
+        !$omp parallel do private(z)
+        InnerLoopOne: do z=1,10
+           array(z) = 20
+        enddo InnerLoopOne
+        !$omp end parallel do
+     enddo OuterLoopTwo
+  enddo OuterLoopOne
+  !$omp end teams distribute
+  !$omp end target
+  ! Expected to print all 20's
+  print *, array
+end program main
+
+! CHECK: 20 20 20 20 20 20 20 20 20 20